aiji-logo

A curated collection of inspirational AI-powered JavaScript apps

footer-icon

Built by Elle, Asim, Osama - hosted on Azure

Cart-Pole Simulation


Solving the classic cart-pole balancing problem with TensorFlow.js

DemoCodeLink

  • TensorFlow.js
  • Reinforcement Learning

Animation

This project is trying to solve the classic cart-pole balancing problem, sometimes refered to as the 'hello world' of reinforcement learning.

Specifically, it showcases an implementation of the policy-gradient method in TensorFlow.js with a combination of the layers and gradients API. Try the demo here to visualise, the training and testing in the browser.

Please train this on a laptop or desktop only.